aiminute. ← All AI news
Research AI Minute Newsroom 2026-11-18

An AI coding agent finds a critical security flaw in Java.

An AI coding agent finds a critical security flaw in Java.

Security startup Calif used OpenAI's Codex coding agent to find a critical flaw in the Java programming language. The bug, named Java4Shell, lets attackers run code on servers without logging in. Oracle and the OpenJDK project released fixes on Tuesday for the four affected Java versions. (Correction: human developers had publicly reported this bug in September; Calif's AI-assisted work rediscovered it independently and showed it could be exploited.)

Why it mattersJava runs much of the world's banking and business software, so patching will take weeks. The researchers say most of the AI's early findings were useless before the real one.
#Coding

✓ Verified · 4 sources

WhatsApp X Telegram
Read in the app — free, in 9 languages

Related stories

Ruby fixes a critical flaw that AI tools helped uncover.
2026-11-19
The IEA expects $4 trillion more in data center spending this decade.
2026-11-19
OpenAI says its models improved AMD's flagship graphics chip design.
2026-11-19
OpenAI says agents finish 46% of its researchers' half-day tasks.
2026-11-19
Four security teams used AI to find the same critical Nginx flaws.
2026-11-19